Skip to content

saikrithik/JanataHack-Recommendation-Systems

Repository files navigation

JanataHack-Recommendation-Systems

Rank 7 Solution for JanathaHack: Recommendation System
The client has provided you with history of last 10 challenges the user has solved, and you need to predict which might be the next 3 challenges the user might be interested to solve. Apply your data science skills to help the client make a big mark in their user engagements/revenue.

Data Description at a Glance

Markdown Monster icon Markdown Monster icon

Train Data at a Glance

Markdown Monster icon

Test Data at a Glance

Markdown Monster icon

Challenge Data at a Glance

Markdown Monster icon

Description of my Methodologies

Approach

1. Initial Try with LSTM

  • Taken a Text Generation Approach and tried training with each sequence combination Ex: for sequence (1,2,3,4,5,6...10) I have taken taken combinations of (1,2-->3), (1,2,3-->4), (1,2,3,4-->5)...
  • This Approach gave me a score of 0.05 map which is very less to start with.

2. Turicreate API

  • After Lot of effort in LSTM(which i couldnt improve) i searched how else can we solve this problem and found that turicreate API works very well with out any actual training. It is suggested to use this API for quick and better solutions of recommendation Link to Turicreate
  • Using Turicreate Itemsimilarity recommender gave me a score of 0.2011 map.

3. LSTM Again

  • Not satisfied with the 0.201 score and again tried various approaches of input data.
  • Finally FinalLSTM.py approach worked , check it Here

Tools used

  1. Python for programming
  2. pandas and numpy libraries for methodology
  3. Tensorflow and keras library for the model
  4. matplotlib and seaborn was used for plotting and analyzing the data

Credits:

Final Approach is taken from McKinsey Analytics Online Hackathon- Recommendation Design Here

Competition Result

Rank: 7th on public LB and 7th on private LB
Link

About

Rank 7th/12053 Solution in JanathaHack: Recommendation System

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published